NEURAL NETWORK BASED CLASSFIER FOR SEPARATING AUDIO SOURCES FROM MONOPHONIC AUDIO SIGNAL Russian patent published in 2011 - IPC G10L15/16 

FIELD: physics.

SUBSTANCE: method is realised by breaking the monophonic audio signal into baseline frames (possibly overlapping), windowing the frames, extracting a number of descriptive features in each frame, and employing a pre-trained nonlinear neural network as a classifier. Each neural network output manifests the presence of a pre-determined type of audio source in each baseline frame of the monophonic audio signal. The classifier output signals can be used as input signals to create multiple audio channels for a source separation algorithm (e.g., ICA) or as parametres in a post-processing algorithm (e.g. categorise music, track sources, generate audio indices for the purposes of navigation, re-mixing, security and surveillance, telephone and wireless communications, and teleconferencing).

EFFECT: network classifier is well suited to address widely changing parametres of the signal and sources, time and frequency domain overlapping of the sources, and reverberation and occlusions in real-life signals.

28 cl, 14 dwg